3.54M parameters
Safetensors metadata reports 3,540,265 parameters, or about 3.54M.
Open Source Model Profile · google
mobilenet_v2_1.0_224
MobileNet V2 1.0 224 is a 3.54M-parameter image-classification model from Google. The captured model card describes ImageNet-1k pretraining at 224x224 resolution.
- Publisher
- Task
- image-classification
- Model type
- mobilenet_v2
- License
- other
- Library
- transformers
- Publication status
- Approved for indexing
Model overview
Google publishes mobilenet_v2_1.0_224 as an image-classification model on the Transformers stack. Captured config identifies MobileNetV2ForImageClassification with a mobilenet_v2 model type, and Safetensors metadata reports 3,540,265 parameters. The captured model card, which notes it was written by the Hugging Face team, describes ImageNet-1k pretraining at 224x224 and an other license value in card data.
Recorded capabilities
ImageNet-1k 224x224 training note
The captured model card describes a MobileNet V2 checkpoint pretrained on ImageNet-1k at 224x224, with 1.0 as the depth multiplier in the checkpoint name.
Transformers image-classification API
The card shows loading AutoImageProcessor and AutoModelForImageClassification to classify an example image into ImageNet classes.
Other licensing
Captured metadata records an other license value.
Use cases in the source record
- Image classification into the card's documented 1,000 ImageNet classes using Transformers AutoImageProcessor and AutoModelForImageClassification.
Limitations and unknowns
- No evaluation results were extracted from this record.
- Provider state is historical snapshot data, not independently refreshed current availability.
- The captured model card states it was written by the Hugging Face team rather than the original MobileNet V2 authors. Pretraining, resolution, and README performance language are publisher/card claims, not independently verified Ethen facts.
Source and provenance
Source: google/mobilenet_v2_1.0_224
Captured: Unknown. Processed: 2026-09-07T19:34:45.932730+00:00.
MobileNet V2 MobileNet V2 model pre-trained on ImageNet-1k at resolution 224x224. It was introduced in MobileNetV2: Inverted Residuals and Linear Bottlenecks by Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen. It was first released in this repository . Disclaimer: The team releasing MobileNet V2 did not write a model card for this model so this model card has been written by the Hugging Face team. Model description From the original README : MobileNets are small, low-latency, low-power models parameterized to meet the resource constraints of a variety of use cases. They can be built upon for classificat…
F001F002F003F004F005F006F007F008F010F011F012F013F014F015